Triple

T22717875
Position Surface form Disambiguated ID Type / Status
Subject PPR E561781 entity
Predicate partOfIndex P5722 FINISHED
Object CAC 40 NE NERFINISHED

How this triple was built (2 steps)

Every LLM step that produced this triple, in pipeline order — named-entity classification, the disambiguation choices (the exact options shown, with the pick highlighted), and the generated description. The batch + timestamp of each is in the Provenance table below.

NER Named-entity recognition gpt-5-mini
Instruction
Given a phrase, classify it is english named entity (e.g., persons, organizations, works of art) in Latin script, or not (e.g., literals, dates, URLs, verbose phrases). For disambiguation, the statement where the phrase occurs as object is also given. Please return a JSON object with `phrase` (string, the phrase being analyzed) and `is_ne` (boolean, indicating whether the phrase is a Named Entity).
Input
Phrase: CAC 40 | Statement: [PPR, partOfIndex, CAC 40]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: CAC 40
Context triple: [PPR, partOfIndex, CAC 40]
  • A. CAC 40 chosen
    CAC 40 is the benchmark French stock market index, tracking 40 major companies listed on the Euronext Paris exchange.
  • B. Euronext 100
    The Euronext 100 is a blue-chip stock market index comprising the largest and most actively traded companies listed on the pan-European Euronext exchange.
  • C. Swiss Market Index
    The Swiss Market Index is Switzerland’s leading stock market benchmark, comprising the largest and most liquid blue-chip companies traded on the SIX Swiss Exchange.
  • D. S&P Europe 350
    S&P Europe 350 is a major stock market index that tracks the performance of 350 leading blue-chip companies across developed European markets.
  • E. STOXX Europe 50
    STOXX Europe 50 is a leading blue-chip stock index comprising 50 of the largest and most liquid companies across European markets.
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.

Provenance (2 batches)

The batch behind each pipeline step, in order, with when it ran. Timestamps are batch-level — stages were processed in waves, so the object chain (NER → NED1 → NEDg → NED2) reads in order, but predicate / elicitation batches can sit in a different wave.

Step Stage Batch ID Status When
creating Elicitation batch_69e2454fc984819088213b58ee87a002 completed April 17, 2026, 2:35 p.m.
NER Named-entity recognition batch_69f1790ecbc48190926d16b20b674dbd completed April 29, 2026, 3:20 a.m.
Created at: April 17, 2026, 3:19 p.m.